Spectral Envelope Statistics for Source Modeling in Speech Enhancement

S. Das, A. Craciun, T. Jaehnel, T. Baeckstroem

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Source modeling is an efficient tool in speech and audio coding, yet in enhancement applications it has been less extensively employed. Incorporating speech source models from coding to enhancement has been difficult because the models are based on linear prediction, which is non-linear in the frequency domain. In this paper we propose a speech source model based on distribution quantizer, which quantifies the coarse shape of the spectral envelope. The spectral envelope is thus described by a set of parameters whose probability distributions have a simple form. The source parameters are estimated using these probability distributions from a single-channel noisy observation by maximum likelihood. Our experiments show that the proposed method is able to track the signal-to-noise ratio with good accuracy. In addition, although trained only on English items, our method showed relatively good results for German items as well, which demonstrates the robustness of the estimated source models.
Original languageEnglish
Title of host publicationSpeech Communication; 12. ITG Symposium
PublisherVDE Verlag
Number of pages5
ISBN (Print)978-3-8007-4275-2
Publication statusPublished - 2016
MoE publication typeA4 Article in a conference publication
EventITG Symposium on Speech Communication - Paderborn, Germany
Duration: 5 Oct 20167 Oct 2016
Conference number: 12


ConferenceITG Symposium on Speech Communication


Dive into the research topics of 'Spectral Envelope Statistics for Source Modeling in Speech Enhancement'. Together they form a unique fingerprint.

Cite this